回复
HarmonyOS Next 利用Core Vision Kit文本识别 原创
第一小趴菜
发布于 2024-11-30 19:30
浏览
0收藏
前言
Core Vision Kit(基础视觉服务)是机器视觉相关的基础能力,例如通用文字识别(即OCR,Optical Character Recognition,也称为光学字符识别)、人脸检测、人脸比对以及主体分割等能力。
步骤
1.创建一个ImageOCRUtil类
创建一个ImageOCRUtil类,用于封装OCR相关功能。
import { textRecognition } from '@kit.CoreVisionKit';
export class ImageOCRUtil {}
export default new ImageOCRUtil();
我们要在ImageOCRUtil中完成文字识别功能。 我们构建一个recognizeText方法,其中其中PixelMap为图像像素类,用于读取或写入图像数据以及获取图像信息。
export class ImageOCRUtil {
/**
* 文字识别
*
* @param image 图片源数据
* @param resultCallback 结果返回
* @returns
*/
async recognizeText(image: PixelMap | undefined, resultCallback: Function) {
if (!image || image === undefined) {
hilog.error(0x0000, 'OCR', 'the image is not existed');
return;
}
let visionInfo: textRecognition.VisionInfo = {
pixelMap: image
};
let textConfiguration: textRecognition.TextRecognitionConfiguration = {
isDirectionDetectionSupported: false
};
textRecognition.recognizeText(visionInfo, textConfiguration, (error: BusinessError, data: textRecognition.TextRecognitionResult) => {
// 识别成功,获取结果
if (error.code == 0) {
let recognitionRes = data.toString();
// 将识别结果返回
resultCallback(recognitionRes);
}
});
}
}
在ImageOCRUtil中,我们用Core File Kit,来选择图片的存储路径,将其加载到我们的页面中,从而实现识别文本
import { picker } from '@kit.CoreFileKit';
openAlbum(): Promise<string> {
return new Promise<string>((resolve, reject) => {
let photoPicker = new picker.PhotoViewPicker;
photoPicker.select({
MIMEType: picker.PhotoViewMIMETypes.IMAGE_TYPE,
maxSelectNumber: 1
}).then((res: picker.PhotoSelectResult) => {
resolve(res.photoUris[0]);
}).catch((err: BusinessError) => {
hilog.error(0x0000, "OCR", `Failed to get photo uri, code: ${err.code}, message: ${err.message}`)
resolve('')
})
})
}
import { image } from '@kit.ImageKit'
import { hilog } from '@kit.PerformanceAnalysisKit';
import ImageOCRUtil from '../common/utils/ImageOCRUtil';
import CommonUtils from '../common/utils/CommonUtils';
import { fileIo } from '@kit.CoreFileKit';
@Entry
@Component
struct Index {
private imageSource: image.ImageSource | undefined = undefined;
@State selectedImage: PixelMap | undefined = undefined;
@State dataValues: string = '';
build() {
Column() {
// 我们的图片
Image(this.selectedImage)
.objectFit(ImageFit.Fill)
.height('60%')
// 我们识别到的内容
Text(this.dataValues)
.copyOption(CopyOptions.LocalDevice)
.height('15%')
.width('60%')
.margin(10)
// 选择图片的按钮
Button('选择图片')
.type(ButtonType.Capsule)
.fontColor(Color.White)
.width('80%')
.margin(10)
.onClick(() => {
this.selectImage();
})
Button('开始识别')
.type(ButtonType.Capsule)
.fontColor(Color.White)
.alignSelf(ItemAlign.Center)
.width('80%')
.margin(10)
.onClick(() => {
// 开始识别的逻辑
});
})
}
.width('100%')
.height('100%')
.justifyContent(FlexAlign.Center)
}
private async selectImage() {
let uri = await ImageOCRUtil.openAlbum();
if (uri === undefined) {
hilog.error(0x0000, 'OCR', 'Failed to get the uri of photo.')
return;
}
this.loadImage(uri);
}
loadImage(path: string) {
setTimeout(async () => {
let fileSource = await fileIo.open(path, fileIo.OpenMode.READ_ONLY);
this.imageSource = image.createImageSource(fileSource.fd);
this.selectedImage = await this.imageSource.createPixelMap();
})
}
}
点击开始识别后,我们就可以通过ImageOCRUtil中的recognizeText,通过回调显示我们识别的结果,然后我们要释放内存,对imageSource和selectedImage进行release()操作
ImageOCRUtil.recognizeText(this.selectedImage, (content: string) => {
if (!CommonUtils.isEmpty(content)) {
this.dataValues = content;
}
this.imageSource?.release();
this.selectedImage?.release();
});
©著作权归作者所有,如需转载,请注明出处,否则将追究法律责任
赞
1
收藏
回复
相关推荐